Remerciez-le!

Remerciez @Admin pour avoir partagé cet document gratuitement, de la manière la plus simple, en partageant sur les réseaux sociaux.

Exploiting poi specific geographical influence for point of interest recommendation

Proceedings of the Twenty-Seventh International Joint Conference on Arti ?cial Intelligence IJCAI- Exploiting POI-Speci ?c Geographical In uence for Point-of-Interest Recommendation Hao Wang Huawei Shen Wentao Ouyang Xueqi Cheng Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China wanghao software ict ac cn shenhuawei ouyangwt cxq ict ac cn Abstract Point-of-Interest POI recommendation i e recommending unvisited POIs for users is a fundamental problem for location-based social networks POI recommendation distinguishes itself from traditional item recommendation e g movie recommendation via geographical in uence among POIs Existing methods model the geographical in uence between two POIs as the probability or propensity that the two POIs are co-visited by the same user given their physical distance These methods assume that geographical in uence between POIs is determined by their physical distance failing to capture the asymmetry of geographical in uence and the high variation of geographical in uence across POIs In this paper we exploit POI-speci ?c geographical in uence to improve POI recommendation We model the geographical in uence between two POIs using three factors the geo-in uence of POI the geosusceptibility of POI and their physical distance Geo-in uence captures POI ? s capacity at exerting geographical in uence to other POIs and geosusceptibility re ects POI ? s propensity of being geographically in uenced by other POIs Experimental results on two real- world datasets demonstrate that POI-speci ?c geographical in uence signi ?cantly improves the performance of POI recommendation Introduction Location-based social networks LBSNs such as Foursquare and Gowalla are increasingly popular bridging the gap between the physical world and online social networking services Xiao et al Sun et al In LBSNs users share their locations and content associated with location information facilitating the understanding of users ? preference and behavior Bao et al Liu and Xiong Gao et al Wang et al a Point-of-Interest POI recommendation i e recommending for users unvisited POIs e g restaurants shopping malls and theaters according to users ? check-in records gains great research in- terest in the last few years Li et al He et al Zhang et al Li et al One of the most prominent features for POI recommendation is that locations of POIs and target user are critical factors for recommendation For example in Gowalla and Foursquare of users ? consecutive check-ins are within the distance less than km Liu et al Therefore besides modeling users ? preference from the interaction between users and POIs as done in traditional item recommendation researchers devote to exploiting the geographical proximity or geographical in uence among POIs to improve the performance of POI recommendation Ye et al Lian et al Xie et al Existing methods that exploit geographical in uence for POI recommendation roughly falls into two paradigms The ?rst kind of methods leverages the geographical proximity to improve the learning of users ? preference assuming that POIs in close proximity to each other share similar user preferences Liu et al Li